 Kerfuffle
|
74d4cfa343
Allow "quantizing" to f16 and f32 (#1787)
|
2 lat temu |
 Kawrakow
|
74a6d922f1
Metal implementation for all k_quants (#1807)
|
2 lat temu |
 slaren
|
e4caa8da59
ci : run when changing only the CUDA sources (#1800)
|
2 lat temu |
 Howard Su
|
58970a4c39
Leverage mmap for offloading tensors to GPU (#1597)
|
2 lat temu |
|
Kawrakow
|
8c0a10e64d
metal : fix failure to load model (#1817)
|
2 lat temu |
|
Kerfuffle
|
fa84c4b3e8
Fix issue where interactive mode crashes when input exceeds ctx size (#1789)
|
2 lat temu |
 Kyle Liang
|
12b063f0ec
Fixed WSL cuda's OOM error (#1594)
|
2 lat temu |
 Ryan Landay
|
31d2b5f4a4
Update SHA256SUMS with current hashes for models quantized using q4_0 (#1798)
|
2 lat temu |
 Georgi Gerganov
|
4de0334f5c
cmake : fix Metal build (close #1791)
|
2 lat temu |
 Artyom Lebedev
|
3f1223155a
k-quants : GCC12 compilation fix (#1792)
|
2 lat temu |
 Andrei
|
303f5809f1
metal : fix issue with ggml-metal.metal path. Closes #1769 (#1782)
|
2 lat temu |
 Aisuko
|
059e99066d
doc : fix wrong address of BLIS.md (#1772)
|
2 lat temu |
|
Georgi Gerganov
|
17c10acfb4
ggml : force no_alloc == false when creating opt tensors (close #1699)
|
2 lat temu |
|
Kawrakow
|
e9b66ee982
metal : add Q4_1 implementation (#1785)
|
2 lat temu |
|
Kerfuffle
|
4f0154b0ba
llama : support requantizing models instead of only allowing quantization from 16/32bit (#1691)
|
2 lat temu |
 Xingchen Song(宋星辰)
|
ef3171d162
ggml : workaround for missing _mm256_setr_m128i in GCC < 8 (#1638)
|
2 lat temu |
 rankaiyx
|
555275a693
make : add SSSE3 compilation use case (#1659)
|
2 lat temu |
 Robert Sung-wook Shin
|
98ed165574
OpenCL: Add release memory (#1741)
|
2 lat temu |
 Johannes Gäßler
|
ae9663f188
Windows nvcc workaround (#1753)
|
2 lat temu |
|
Georgi Gerganov
|
b33dee282f
metal : fix build "tanhf" -> "tanh"
|
2 lat temu |
 AT
|
92f44ff7f7
metal : add GELU implementation (#1770)
|
2 lat temu |
|
Kawrakow
|
245fc3c37d
metal : faster q4_0 (#1775)
|
2 lat temu |
|
Kawrakow
|
72ff5282bf
metal : add Q2_K implementation (#1762)
|
2 lat temu |
|
Georgi Gerganov
|
0bf7cf1b29
Revert "ggml : load data into int8x16x4_t using vld4q_s8 on arm64 (#1738)"
|
2 lat temu |
 le.chang
|
8432d4d9f7
ggml : load data into int8x16x4_t using vld4q_s8 on arm64 (#1738)
|
2 lat temu |
|
Kawrakow
|
0f291e1f65
metal : Q6_K implementation (#1752)
|
2 lat temu |
 qingfengfenga
|
8fc8179919
Add llama.cpp docker support for non-latin languages (#1673)
|
2 lat temu |
 Steven Roussey
|
b50b570ed9
ggml : fix fprintf warnings (#1720)
|
2 lat temu |
|
Georgi Gerganov
|
53aba3f393
clang-tidy : restore dot file from accidental deletion
|
2 lat temu |
|
Kawrakow
|
4161bdc04d
metal : add Q4_K implementation (#1733)
|
2 lat temu |
